Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to previous versions or states in a comparison context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    price to discount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.55
    Diweddarwch
    -0.50
     kasarigan
    -0.47
     CanadaChoose
    -0.45
    PositiveButton
    -0.44
    glLoad
    -0.43
     noDo
    -0.42
     Kaufmann
    -0.42
    lccn
    -0.41
     invokingState
    -0.41
    POSITIVE LOGITS
     semula
    0.47
     zmieni
    0.46
    原本
    0.44
     devenus
    0.43
    เดิม
    0.42
     Мексичка
    0.41
    原来的
    0.41
     originalmente
    0.40
     oldValue
    0.39
     newOwner
    0.39
    Act Density 0.318%

    No Known Activations